© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 41917
    Prev
    Next
    INDEX
    Explanations

    course descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    $.}
    0.91
    $.
    0.85
    ate
    0.82
    words
    0.81
    angle
    0.80
    artifact
    0.80
    0
    0.79
    arse
    0.78
    umls
    0.78
     armas
    0.75
    POSITIVE LOGITS
    Ни
    0.88
     earns
    0.80
     eliminates
    0.77
     exemplifies
    0.73
     Inspectors
    0.73
    দ
    0.73
    Что
    0.73
     defies
    0.72
    ل
    0.72
    ת
    0.72
    Activations Density 0.000%

    No Known Activations